cls_report =               precision    recall  f1-score   support

         0.0     0.8916    0.7957    0.8409        93
         1.0     0.8537    0.8537    0.8537        82
         2.0     0.6962    0.6875    0.6918        80
         3.0     1.0000    1.0000    1.0000        57
         4.0     0.7714    0.8308    0.8000        65
         5.0     0.9494    0.9740    0.9615        77
         6.0     0.9889    1.0000    0.9944        89
         7.0     0.9474    0.9863    0.9664        73
         8.0     1.0000    1.0000    1.0000        13
         9.0     1.0000    1.0000    1.0000         9

    accuracy                         0.8903       638
   macro avg     0.9098    0.9128    0.9109       638
weighted avg     0.8903    0.8903    0.8897       638

eval_loss = 0.29622152000665664
macro_f1 = 0.9108786349245351
macro_p = 0.9098480303268863
macro_r = 0.9127954035974767
mcc = 0.8756280066894239